Deep Cross-Modal Steganography Using Neural Representations

TL;DR

This paper introduces a deep cross-modal steganography framework leveraging Implicit Neural Representations to embed diverse secret data types into cover images, enhancing flexibility and modality compatibility.

Contribution

It presents a novel INR-based deep steganography method capable of handling multiple data modalities, addressing limitations of existing techniques.

Findings

Effective embedding of various secret data types.

High expandability across different modalities.

Maintains cover image quality during embedding.

Abstract

Steganography is the process of embedding secret data into another message or data, in such a way that it is not easily noticeable. With the advancement of deep learning, Deep Neural Networks (DNNs) have recently been utilized in steganography. However, existing deep steganography techniques are limited in scope, as they focus on specific data types and are not effective for cross-modal steganography. Therefore, We propose a deep cross-modal steganography framework using Implicit Neural Representations (INRs) to hide secret data of various formats in cover images. The proposed framework employs INRs to represent the secret data, which can handle data of various modalities and resolutions. Experiments on various secret datasets of diverse types demonstrate that the proposed approach is expandable and capable of accommodating different modalities.